Posters

UltraPixel generates high-quality images at various resolutions (1K-6K) efficiently using cascade diffusion models, achieving state-of-the-art performance.

A revolutionary ultrafast phylogenetic method outperforms protein language models in variant effect prediction by efficiently estimating amino acid substitution rates from massive datasets.

UGC: Blazing-fast graph coarsening for big data, preserving key insights across diverse graph types.

UDPM: Upsampling Diffusion Probabilistic Models achieves high-quality image generation with fewer computations by incorporating downsampling and upsampling within the diffusion process.

UDON: a novel multi-teacher online distillation method creates highly efficient universal image embeddings by dynamically transferring domain-specific knowledge and adapting to imbalanced data.

A unified neural divide-and-conquer framework (UDC) achieves superior performance on large-scale combinatorial optimization problems by employing a novel Divide-Conquer-Reunion training method and a h…

U-DiT: Revolutionizing diffusion transformers with a U-Net design and token downsampling for superior image generation and drastically reduced computation cost.

Typicalness-Aware Learning (TAL) improves failure detection by dynamically adjusting prediction confidence based on sample typicality, mitigating overconfidence and achieving significant performance g…

Two-way Deconfounder tackles off-policy evaluation challenges by introducing a novel two-way unmeasured confounding assumption and a neural-network-based deconfounder, achieving consistent policy valu…

Twin-Merging dynamically merges modular model expertise, significantly improving multitask performance without retraining, and adapting to diverse data.

TurboHopp: 30x faster 3D scaffold hopping with consistency models, boosting drug discovery!

TuneTables optimizes PFNs for scalability via context optimization, achieving state-of-the-art performance on large tabular datasets while using fewer parameters and reducing inference time.

TSDS: A novel framework selects optimal training data for efficient large language model finetuning using only a few examples, boosting performance.

Researchers developed Subsampled Smooth Calibration Error (SSCE), a new truthful calibration measure for sequential prediction, solving the problem of existing measures being easily gamed.

This paper presents a novel, truthful, and privacy-preserving mechanism for high-dimensional sparse linear regression, incentivizing data contribution while safeguarding individual privacy.

LLM lie detectors fail to generalize; this paper presents a robust method achieving 94% accuracy by identifying a universal two-dimensional truth subspace, separating true/false statements across vari…

Faster algorithms for solving discounted Markov Decision Processes (DMDPs) are introduced, achieving near-optimal sample and time complexities, especially in the sample setting and improving runtimes …

TripletCLIP boosts CLIP’s compositional reasoning by cleverly generating synthetic hard negative image-text pairs, achieving over 9% absolute improvement on SugarCrepe.

LLM-powered Tri-level learning framework enhances time series OOD generalization.

TreeVI: Scalable tree-structured variational inference captures instance-level correlations for improved model accuracy.